Autonomous Ground Vehicles Research Articles

Learning-Based $H_\infty$ Path-Following Controller Design for Autonomous Ground Vehicles Subject to Stochastic Delays and Actuator Constraints

In order to decrease computation loads for path following control of autonomous ground vehicles (AGVs), in this article, we aim to design an output-feedback path following controller by using a learning-based least squares support vector machine (LS-SVM) model. The signal transmission delay, which would deteriorates the control performance, is considered as well. First, the LS-SVM model for vehicle path following system is trained. Then, the output-feedback controller subject to stochastic communication delay, which meets the stability condition, is designed for the LS-SVM model. The modeling error and bias terms of LS-SVM model are regarded as the disturbance term. In order to attenuate the effect of disturbance, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$H_\infty$</tex-math></inline-formula> controller is designed for the AGVs to track the target path. Grey wolf optimizer is employed to solve the controller design problem with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$H_\infty$</tex-math></inline-formula> performance and transform stability condition from bilinear matrix inequality to linear matrix inequality (LMI). Then, we employ efficient LMI toolbox to solve the LMI. To guarantee the effectiveness of proposed controller, characteristics of steering wheel in a hardware-in-loop platform are studied and rate of steering angle is regarded as the actuator constraints for designing controller. Experimental results based on the hardware-in-loop platform have verified the effectiveness of the proposed control strategy.

CARMA II: A ground vehicle for autonomous surveying of alpha, beta and gamma radiation.

Surveying active nuclear facilities for spread of alpha and beta contamination is currently performed by human operators. However, a skills gap of qualified workers is emerging and is set to worsen in the near future due to under recruitment, retirement and increased demand. This paper presents an autonomous ground vehicle that can survey nuclear facilities for alpha, beta and gamma radiation and generate radiation heatmaps. New methods for preventing the robot from spreading radioactive contamination using a state-machine and radiation costmaps are introduced. This is the first robot that can detect alpha and beta contamination and autonomously re-plan around the contamination without the wheels passing over the contaminated area. Radiation avoidance functionality is proven experimentally to reduce alpha and beta contamination spread as well as gamma radiation dose to the robot. The robot's survey area is defined using a custom designed, graphically controlled area coverage planner. It was concluded that the robot is highly suited to certain monotonous room scale radiation surveying tasks and therefore provides the opportunity for financial savings, to mitigate a future skills gap, and provision of radiation surveys that are more granular, accurate and repeatable than those currently performed by human operators.

Observer-Based Path Tracking Controller Design for Autonomous Ground Vehicles With Input Saturation

This paper investigates the problem of path tracking control for autonomous ground vehicles (AGVs), where the input saturation, system nonlinearities and uncertainties are considered. Firstly, the nonlinear path tracking system is formulated as a linear parameter varying (LPV) model where the variation of vehicle velocity is taken into account. Secondly, considering the noise effects on the measurement of lateral offset and heading angle, an observer-based control strategy is proposed, and by analyzing the frequency domain characteristics of the derivative of desired heading angle, a finite frequency <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$H_{\infty}$</tex> index is proposed to attenuate the effects of the derivative of desired heading angle on path tracking error. Thirdly, sufficient conditions are derived to guarantee robust <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$H_{\infty}$</tex> performance of the path tracking system, and the calculation of observer and controller gains is converted into solving a convex optimization problem. Finally, simulation examples verify the advantages of the control method proposed in this paper.

LiDAR SLAM with a Wheel Encoder in a Featureless Tunnel Environment

Simultaneous localization and mapping (SLAM) represents a crucial algorithm in the autonomous navigation of ground vehicles. Several studies were conducted to improve the SLAM algorithm using various sensors and robot platforms. However, only a few works have focused on applications inside low-illuminated featureless tunnel environments. In this work, we present an improved SLAM algorithm using wheel encoder data from an autonomous ground vehicle (AGV) to obtain robust performance in a featureless tunnel environment. The improved SLAM system uses FAST-LIO2 LiDAR SLAM as the baseline algorithm, and the additional wheel encoder sensor data are integrated into the baseline SLAM structure using the extended Kalman filter (EKF) algorithm. The EKF algorithm is used after the LiDAR odometry estimation and before the mapping process of FAST-LIO2. The prediction step uses the wheel encoder and inertial measurement unit (IMU) data, while the correction step uses the FAST-LIO2 LiDAR state estimation. We used an AGV to conduct experiments in flat and inclined terrain sections in a tunnel environment. The results showed that the mapping and the localization process in the SLAM algorithm was greatly improved in a featureless tunnel environment considering both inclined and flat terrains.

Deep neural networks to predict autonomous ground vehicle behavior on sloping terrain field

AbstractConventional large agricultural machinery or implements are unsafe and unsuitable to operate on slopes or 10%. Tractor rollovers are frequent on slopes, precluding farming on arable hills, uneven or highly sloped land. Therefore, a fleet of autonomous ground vehicles (AGV) is proposed to cultivate highly sloped land (). The fleet aims to expand agricultural land to the slopes and to strengths the human‐robot collaboration in an unsafe sloped environment. However, the fleet's success largely depends on vehicle behavior models regarding traction, mobility, and energy consumption on varying slopes. The vehicle intelligent behavior models are essential and would solve multiple objectives ranging from simulations to path planning &amp; navigation. Therefore, this study aimed to build a deep learning‐based vehicle behavior models on sloping terrain. A standard drawbar test was performed on a single AGV operating on an actual sloped field at varying speeds and load conditions. The drawbar test quantified the AGV's behavior on slopes in metrics related to traction (traction efficiency), mobility (travel reduction), and energy consumption (power number). Deep learning‐based models were developed from the experimental data to predict the AGV's behavior on slopes as a function of vehicle velocity, drawbar, and slope. A special model called the proposed model, which combined multiple deep neural networks with a mixture of Gaussians, was developed and trained with a hybrid training method. The proposed model consistently outperformed the other well‐known machine learning models. This study explored the capabilities of machine learning algorithms to simulate the behavior of small‐track vehicle or AGV on sloping terrain. The fleet aims to provide safer agriculture keeping human safety in focus, and the developed predictive vehicle behavior models would empower the fleet's operation on currently unsafe sloped terrain by assisting in vehicle path planning, route optimization, and decision making.

Research on trajectory tracking and body attitude control of autonomous ground vehicle based on differential steering.

The differential steering can be used not only as the backup system of steer-by-wire, but also as the only steering system. Because the differential steering is realized through the differential moment between the coaxial left and right driving wheels, the sharp reduction of the load on the inner driving wheel will directly lead to the failure of the differential steering when the four-wheel independent drive electric vehicle approaches the rollover. Therefore, this paper not only realizes the trajectory tracking of autonomous ground vehicle through the differential steering, but also puts forward the body attitude control to improve the handling stability. Firstly, the dynamic and kinematic models of differential steering autonomous ground vehicle (DSAGV) and its roll model are established, and the linear three-degree of freedom vehicle model is selected as the reference model to generate the ideal body roll angle. Secondly, a model predictive controller (MPC) is designed to control the DSAGV to track the given reference trajectory, and obtain the required differential moment and the resulting front-wheel steering angle. Then, a sliding mode controller (SMC) is adopted to control the DSAGV to track the ideal body roll angle, and obtain the required roll moment. The simulation results show that the proposed MPC and SMC can not only make the DSAGV realize the trajectory tracking, but also achieve the body attitude control.

Cooperative control and stability analysis for virtual coupling of rail vehicles

Cooperative control for rail vehicles is a new idea which builds on existing models and methods developed in the context of flight formation and autonomous ground vehicles. The underlying idea is to assimilate virtually coupled rail vehicles to arrays of mass–spring–dashpot systems. The contribution of this paper is three-fold. First, a novel scheme is proposed which involves a supervisory control for the higher-level planning and a local motion coordination for the lower-level implementation. For the supervisory control, a review of the existing scheduling models and methods based on alternate graphs and a mixed-integer (non)linear program is conducted. For the local coordination, a nonlinear and uncertain model is developed and a constructive method is provided to design a feedback control that stabilizes the vehicle around a desired equilibrium point, in terms of position and velocity. Second, the control design method is extended to the case of multiple virtually coupled vehicles. It is proven that the transient dynamics follows a typical synchronization dynamics. It is also proven that under such control, the whole system of rail vehicles converges to a pre-defined equilibrium point, characterized by a specific velocity and relative distance between vehicles. Conditions for the stability of such equilibrium points are investigated. Third, under the hypothesis of homogeneity, bounds on the damping coefficient for the synchronization equilibrium (in terms of velocity and relative distance between vehicles) to be overdamped or underdamped are provided.

Low-Latency Edge Video Analytics for On-Road Perception of Autonomous Ground Vehicles

To improve the transportation efficiency of advanced manufacturing, cameras have been extensively deployed to enhance the on-road perception of autonomous ground vehicles in smart industrial parks. Considering the informative yet substantial data volume of contents generated by those cameras, we employ vehicle-to-everything links to deliver the captured video frames to neighboring vehicles, road-side units, or base stations, in order to respond to vehicle-control-related video queries. To help vehicles obtain low-latency and high-accuracy on-road information for autonomous driving, an optimization problem is formulated, taking into account the impact of vehicle mobility and diverse resource demands of different video queries. Then, a two-stage algorithm is proposed to determine the frame rate of video cameras, as well as the destination of the associated video frames based on matching theory. Extensive simulation results show that this approach can improve the accuracy by up to 18% and reduce the response delay by 13.2%.

Energy efficient path planning for autonomous ground vehicles with ackermann steering

The autonomous ground vehicles have attracted a great deal of attention as viable solutions to a wide variety of military and civilian applications. However, the energy consumption plays a major role in the navigation of autonomous ground vehicles in challenging environments, especially if they are left to operate unattended under limited on-board power, such as planetary exploration, border patrol, etc. The autonomous ground vehicles are expected to perform more tasks more efficiently with limited power in these scenarios. Although plenty of research has developed an effective methodology for generating dynamically feasible and energy efficient trajectories for skid steering or differential steering vehicles, few studies on path planning for ackermann steering autonomous ground vehicles are available. In this study, an energy efficient path planning method with guarantee on completeness is proposed for autonomous ground vehicle with ackermann steering which is based on A∗ search algorithm. Firstly, the energy cost model is established for the autonomous ground vehicle using its kinematic constraints. Then, given the start and goal states, the energy-aware motion primitives are generated offline using the energy cost model to calculate the cost of each primary trajectory. Lastly, the energy efficient path planner is proposed and the analysis for completeness properties is given. The effectiveness of the proposed energy efficient path planner is verified by simulation over 150 randomly generated maps and real vehicle tests. The results show that a small increase in the distance of a path over the distance optimal path can result in a reduction of energy cost by nearly 26.9% in simulation and 21.09% in real test scenario for autonomous ground vehicles with ackermann steering.

AutoVRL: A High Fidelity Autonomous Ground Vehicle Simulator for Sim-to-Real Deep Reinforcement Learning

Deep Reinforcement Learning (DRL) enables cognitive Autonomous Ground Vehicle (AGV) navigation utilizing raw sensor data without a-priori maps or GPS, which is a necessity in hazardous, information poor environments such as regions where natural disasters occur, and extraterrestrial planets. The substantial training time required to learn an optimal DRL policy, which can be days or weeks for complex tasks, is a major hurdle to real-world implementation in AGV applications. Training entails repeated collisions with the surrounding environment over an extended time period, dependent on the complexity of the task, to reinforce positive exploratory, application specific behavior that is expensive, and time consuming in the real-world. Effectively bridging the simulation to real-world gap is a requisite for successful implementation of DRL in complex AGV applications, enabling learning of cost-effective policies. We present AutoVRL, an open-source high fidelity simulator built upon the Bullet physics engine utilizing OpenAI Gym and Stable Baselines3 in PyTorch to train AGV DRL agents for sim-to-real policy transfer. AutoVRL is equipped with sensor implementations of GPS, IMU, LiDAR and camera, actuators for AGV control, and realistic environments, with extensibility for new environments and AGV models. The simulator provides access to state-of-the-art DRL algorithms, utilizing a python interface for simple algorithm and environment customization, and simulation execution.

Deep Reinforcement Learning for Autonomous Ground Vehicle Exploration Without A-Priori Maps

Autonomous Ground Vehicles (AGVs) are essential tools for a wide range of applications stemming from their ability to operate in hazardous environments with minimal human operator input. Effective motion planning is paramount for successful operation of AGVs. Conventional motion planning algorithms are dependent on prior knowledge of environment characteristics and offer limited utility in information poor, dynamically altering environments such as areas where emergency hazards like fire and earthquake occur, and unexplored subterranean environments such as tunnels and lava tubes on Mars. We propose a Deep Reinforcement Learning (DRL) framework for intelligent AGV exploration without a-priori maps utilizing Actor-Critic DRL algorithms to learn policies in continuous and high-dimensional action spaces directly from raw sensor data. The DRL architecture comprises feedforward neural networks for the critic and actor representations in which the actor network strategizes linear and angular velocity control actions given current state inputs, that are evaluated by the critic network which learns and estimates Q-values to maximize an accumulated reward. Three off-policy DRL algorithms, DDPG, TD3 and SAC, are trained and compared in two environments of varying complexity, and further evaluated in a third with no prior training or knowledge of map characteristics. The agent is shown to learn optimal policies at the end of each training period to chart quick, collision-free exploration trajectories, and is extensible, capable of adapting to an unknown environment without changes to network architecture or hyperparameters. The best algorithm is further evaluated in a realistic 3D environment.

Communication security of autonomous ground vehicles based on networked control systems: The optimized LMI approach

The paper presents a study of networked control systems (NCSs) that are subjected to periodic denial-of-service (DoS) attacks of varying intensity. The use of appropriate Lyapunov–Krasovskii functionals (LKFs) help to reduce the constraints of the basic conditions and lower the conservatism of the criteria. An optimization problem with constraints is formulated to select the trigger threshold, which is solved using the gradient descent algorithm (GDA) to improve resource utilization. An intelligent secure event-triggered controller (ISETC) is designed to ensure the safe operation of the system under DoS attacks. The approach is validated through experiments with an autonomous ground vehicle (AGV) system based on the Simulink platform. The proposed method offers the potential for developing effective defense mechanisms against DoS attacks in NCSs.

Perceptual Interaction-Based Path Tracking Control of Autonomous Vehicles Under DoS Attacks: A Reinforcement Learning Approach

This paper considers the distributed optimal path tracking control problem of autonomous ground vehicles (AGVs) with matched uncertainties under denial-of-service (DoS) attacks. First, to solve the uncertain system parameters, an inverse reinforcement learning (RL) technique is PROPOSED to seek the optimal controller instead of directly solving the robust control problem, which can ensure that the designed controller is globally optimal with respect to the proposal performance function. An off-policy RL algorithm is further proposed to learn the optimal control solution online without requiring any knowledge of the vehicle dynamics. Then, to lower the communication load among vehicles, a perception-based optimal resilient controller and its corresponding perception-based static deadband condition are developed, respectively. Moreover, the perception-based dynamic deadband control mechanism is further exploited to consider the secure path tracking control problem. The proposed algorithms verify that the RL-based optimal path tracking control can be solved, and the occurrence of the Zeno phenomenon can be avoided. Finally, a numerical simulation is demonstrated to verify the effectiveness of the proposed approach.

Feedback linearisation and disturbance observer based path following control for autonomous ground vehicle

Feedback linearisation and disturbance observer based path following control for autonomous ground vehicle

Vehicle Actuator Fault Detection With Finite-Frequency Specifications via Takagi-Sugeno Fuzzy Observers: Theory and Experiments

This article presents a new nonlinear observer-based method to detect the faults of both steering and torque actuators of autonomous ground vehicles. To this end, the nonlinear vehicle system is reformulated in a Takagi-Sugeno (TS) fuzzy model with both measured and unmeasured nonlinear consequents, called N-TS fuzzy model. Differently from the classical TS fuzzy technique with linear consequents, this N-TS fuzzy reformulation enables an effective use of differential mean value theorem to deal with unmeasured nonlinearities, which is known as a major challenge in TS fuzzy observer design. Moreover, the N-TS fuzzy form also allows reducing not only the design conservatism but also the numerical complexity of the design conditions as well as the observer structure, which is crucial for real-time vehicle application. To minimize the disturbance effect with an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathscr {H}_\infty$</tex-math></inline-formula> performance and maximize the fault sensibility with an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathscr {H}_-$</tex-math></inline-formula> performance, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> information on the disturbance/fault frequency ranges is taken into account in the N-TS fuzzy observer design via the generalized Kalman–Yakubovich–Popov (KYP) lemma. Based on Lyapunov stability theory, the design of the proposed multiobjective <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathscr {H}_-/\mathscr {H}_\infty$</tex-math></inline-formula> N-TS fuzzy fault detector is recast as an optimization problem with strict linear matrix inequality (LMI) constraints, which can be effectively solved with numerical solvers. Both numerical and experiments are performed under realistic driving conditions to demonstrate the theoretical and practical interests of the new finite-frequency fuzzy fault detection method.

Feedback linearisation and disturbance observer based path following control for autonomous ground vehicle

Feedback linearisation and disturbance observer based path following control for autonomous ground vehicle

Multiphase Overtaking Maneuver Planning for Autonomous Ground Vehicles Via a Desensitized Trajectory Optimization Approach

This article studies the problem of trajectory optimization for autonomous ground vehicles with the consideration of irregularly placed on-road obstacles and multiple maneuver phases. By introducing a series of event sequences, a new multiphase constrained optimal control formulation is constructed to describe the automatic overtaking process. Although existing trajectory optimization techniques can be applied to address the constructed problem, they may suffer from poor or premature convergence issues due to the complexity of the mission formulation. Thus, to offer an effective alternative, a novel desensitized trajectory optimization method is designed and implemented to explore the optimal overtaking maneuver for the AGVs. The proposed method applies a double layer structure, where an enhanced intelligent optimization method is used in the outer layer such that the main inner optimization routine can be boosted by starting at a better reference solution. The algorithm convergence as well as the solution optimality conditions are theoretically analyzed. Numerical results are provided to illustrate the validity of the established formulation. Comparative case studies were executed to demonstrate the quality of the obtained solution and the enhanced performance of the proposed trajectory optimization method.

A Robust Intelligent Controller for Autonomous Ground Vehicle Longitudinal Dynamics

In this paper, a novel adaptive sliding mode controller (SMC) was designed based on a robust law considering disturbances and uncertainties for autonomous ground vehicle (AGV) longitudinal dynamics. The robust law was utilized in an innovative method involving the upper bounds of disturbances and uncertainties. Estimating this lumped uncertainty upper limit based on a neural network approach allowed its online knowledge. It guided the controller to withstand the disturbance and to compensate for the uncertainties. A stability analysis, according to Lyapunov, was completed to confirm the asymptotic convergence of the states to the desired state. The effectiveness and benefits of the planned approach were scrutinized by simulations and comparative studies.

Link-Blockage Model and AP-Placement Scheme for No-Blockage Link between AGV and AP in Logistics–Warehousing VLC Network

In this paper, the blockage problem of the optical link between AGV (autonomous ground vehicles) and AP (access point) in the logistics–warehousing VLC (visible light communication) network is analyzed. First, based on the random geometric model, a link-blockage model is proposed. Given the position of AGV, AP and obstacle, the blockage state of the VLC link between AGV and AP can be obtained through this model. Then, an AP-placement scheme based on the link-blockage model is proposed. Under this AP placement, AGVs in any position have a reliable link that is not affected by obstacles. During the movement of AGV, the VLC link of AGV will not be interrupted by a random blockage. Finally, the effectiveness of the link-blockage model is demonstrated by the shadow method. In this paper, the link outage probability and the data rate under different AP heights, AP spacings and the number of obstacles are simulated. Simulation results show that the VLC link can keep uninterrupted under the AP placement proposed in this paper.

Nonlinear H∞ path following control for autonomous ground vehicles via neural network and policy iteration algorithm

This paper addresses the crucial issues of autonomous ground vehicles (AGVs), that is, smooth and accurate path following, especially when input constraints and external disturbances exist. A nonlinear H∞ control scheme is proposed based on the neural network (NN) and policy iteration (PI) algorithm. Firstly, a nonlinear system model for path following of AGVs is constructed, which takes vehicular nonlinear cornering behavior into account. Then, a nonlinear H∞ controller is designed based on the Hamilton-Jacobi-Isaacs (HJI) equation. Wherein, the established NN is leveraged to approximate the HJI equation’s performance function, and the PI algorithm is developed to learn the solution to the HJI equation. Finally, the convergence and closed-loop stability of the proposed strategy are demonstrated. Simulation results show that the proposed controller can significantly improve the response speed, driving smoothness and accuracy of path following in high-speed driving condition with strong robustness against external disturbances.